DeepSeek's WEIRD Behavior: The cultural alignment of Large Language Models and the effects of prompt language and cultural prompting

• URL: http://arxiv.org/abs/2512.09772v2
• Date: Fri, 12 Dec 2025 17:25:30 GMT
• Title: DeepSeek's WEIRD Behavior: The cultural alignment of Large Language Models and the effects of prompt language and cultural prompting
• Authors: James Luther, Donald Brown,
• Abstract summary: We use Hofstede's VSM13 international surveys to understand the cultural alignment of large language models (LLMs)<n>We use a combination of prompt language and cultural prompting, a strategy that uses a system prompt to shift a model's alignment to reflect a specific country.<n>Our results show that DeepSeek-V3, V3.1, and OpenAI's GPT-5 exhibit a close alignment with the survey responses of the United States.<n>We also find that GPT-4 exhibits an alignment closer to China when prompted in English, but cultural prompting is effective in shifting this alignment closer to the United States
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Culture is a core component of human-to-human interaction and plays a vital role in how we perceive and interact with others. Advancements in the effectiveness of Large Language Models (LLMs) in generating human-sounding text have greatly increased the amount of human-to-computer interaction. As this field grows, the cultural alignment of these human-like agents becomes an important field of study. Our work uses Hofstede's VSM13 international surveys to understand the cultural alignment of the following models: DeepSeek-V3, V3.1, GPT-4, GPT-4.1, GPT-4o, and GPT-5. We use a combination of prompt language and cultural prompting, a strategy that uses a system prompt to shift a model's alignment to reflect a specific country, to align these LLMs with the United States and China. Our results show that DeepSeek-V3, V3.1, and OpenAI's GPT-5 exhibit a close alignment with the survey responses of the United States and do not achieve a strong or soft alignment with China, even when using cultural prompts or changing the prompt language. We also find that GPT-4 exhibits an alignment closer to China when prompted in English, but cultural prompting is effective in shifting this alignment closer to the United States. Other low-cost models, GPT-4o and GPT-4.1, respond to the prompt language used (i.e., English or Simplified Chinese) and cultural prompting strategies to create acceptable alignments with both the United States and China.

Related papers

• The American Ghost in the Machine: How language models align culturally and the effects of cultural prompting [0.0]
  We use the VSM13 International Survey and Hofstede's cultural dimensions to identify the cultural alignment of popular Large Language Models (LLMs)<n>We then use cultural prompting to test the adaptability of these models to other cultures, namely China, France, India, Iran, Japan, and the United States.<n>We find that the majority of the eight LLMs tested favor the United States when the culture is not specified, with varying results when prompted for other cultures.
  arXiv  Detail & Related papers  (2025-12-13T23:11:41Z)
• LLMs and Cultural Values: the Impact of Prompt Language and Explicit Cultural Framing [0.21485350418225244]
  Large Language Models (LLMs) are rapidly being adopted by users across the globe, who interact with them in a diverse range of languages.<n>We examine how prompt language and cultural framing influence model responses and their alignment with human values in different countries.
  arXiv  Detail & Related papers  (2025-11-06T02:09:29Z)
• MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation [91.22008265721952]
  MMA-ASIA centers on a human-curated, multilingual, and multimodally aligned benchmark covering 8 Asian countries and 10 languages.<n>This is the first dataset aligned at the input level across three modalities: text, image (visual question answering), and speech.<n>We propose a five-dimensional evaluation protocol that measures: (i) cultural-awareness disparities across countries, (ii) cross-lingual consistency, (iii) cross-modal consistency, (iv) cultural knowledge generalization, and (v) grounding validity.
  arXiv  Detail & Related papers  (2025-10-07T14:12:12Z)
• Cross-Cultural Transfer of Commonsense Reasoning in LLMs: Evidence from the Arab World [68.19795061447044]
  This paper investigates cross-cultural transfer of commonsense reasoning in the Arab world.<n>Using a culturally grounded commonsense reasoning dataset covering 13 Arab countries, we evaluate lightweight alignment methods.<n>Our results show that merely 12 culture-specific examples from one country can improve performance in others by 10% on average.
  arXiv  Detail & Related papers  (2025-09-23T17:24:14Z)
• From Word to World: Evaluate and Mitigate Culture Bias in LLMs via Word Association Test [50.51344198689069]
  We extend the human-centered word association test (WAT) to assess the alignment of large language models with cross-cultural cognition.<n>To address culture preference, we propose CultureSteer, an innovative approach by embedding cultural-specific semantic associations directly within the model's internal representation space.
  arXiv  Detail & Related papers  (2025-05-24T07:05:10Z)
• CulturePark: Boosting Cross-cultural Understanding in Large Language Models [63.452948673344395]
  This paper introduces CulturePark, an LLM-powered multi-agent communication framework for cultural data collection. It generates high-quality cross-cultural dialogues encapsulating human beliefs, norms, and customs. We evaluate these models across three downstream tasks: content moderation, cultural alignment, and cultural education.
  arXiv  Detail & Related papers  (2024-05-24T01:49:02Z)
• Human vs. LMMs: Exploring the Discrepancy in Emoji Interpretation and Usage in Digital Communication [68.40865217231695]
  This study examines the behavior of GPT-4V in replicating human-like use of emojis. The findings reveal a discernible discrepancy between human and GPT-4V behaviors, likely due to the subjective nature of human interpretation.
  arXiv  Detail & Related papers  (2024-01-16T08:56:52Z)
• Not All Countries Celebrate Thanksgiving: On the Cultural Dominance in Large Language Models [89.94270049334479]
  This paper identifies a cultural dominance issue within large language models (LLMs) LLMs often provide inappropriate English-culture-related answers that are not relevant to the expected culture when users ask in non-English languages.
  arXiv  Detail & Related papers  (2023-10-19T05:38:23Z)
• Large language models can replicate cross-cultural differences in personality [0.0]
  We use a large-scale experiment to determine whether GPT-4 can replicate cross-cultural differences in the Big Five.<n>We used the US and South Korea as the cultural pair.
  arXiv  Detail & Related papers  (2023-10-12T11:17:23Z)
• Cultural Alignment in Large Language Models: An Explanatory Analysis Based on Hofstede's Cultural Dimensions [10.415002561977655]
  This research proposes a Cultural Alignment Test (Hoftede's CAT) to quantify cultural alignment using Hofstede's cultural dimension framework. We quantitatively evaluate large language models (LLMs) against the cultural dimensions of regions like the United States, China, and Arab countries. Our results quantify the cultural alignment of LLMs and reveal the difference between LLMs in explanatory cultural dimensions.
  arXiv  Detail & Related papers  (2023-08-25T14:50:13Z)
• Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study [9.919972416590124]
  ChatGPT has garnered widespread recognition for its exceptional ability to generate human-like responses in dialogue. We investigate the underlying cultural background of ChatGPT by analyzing its responses to questions designed to quantify human cultural differences.
  arXiv  Detail & Related papers  (2023-03-30T15:43:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.